Search Results for author: Shyamgopal Karthik

Found 13 papers, 9 papers with code

Vision-by-Language for Training-Free Compositional Image Retrieval

1 code implementation13 Oct 2023 Shyamgopal Karthik, Karsten Roth, Massimiliano Mancini, Zeynep Akata

Finally, we show that CIReVL makes CIR human-understandable by composing image and text in a modular fashion in the language domain, thereby making it intervenable, allowing to post-hoc re-align failure cases.

Image Retrieval Retrieval +1

ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models

1 code implementation ICCV 2023 Uddeshya Upadhyay, Shyamgopal Karthik, Massimiliano Mancini, Zeynep Akata

We propose ProbVLM, a probabilistic adapter that estimates probability distributions for the embeddings of pre-trained VLMs via inter/intra-modal alignment in a post-hoc manner without needing large-scale datasets or computing.

Active Learning Model Selection +1

If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection

1 code implementation22 May 2023 Shyamgopal Karthik, Karsten Roth, Massimiliano Mancini, Zeynep Akata

Despite their impressive capabilities, diffusion-based text-to-image (T2I) models can lack faithfulness to the text prompt, where generated images may not contain all the mentioned objects, attributes or relations.

Text-to-Image Generation

BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks

1 code implementation14 Jul 2022 Uddeshya Upadhyay, Shyamgopal Karthik, Yanbei Chen, Massimiliano Mancini, Zeynep Akata

Moreover, many of the high-performing deep learning models that are already trained and deployed are non-Bayesian in nature and do not provide uncertainty estimates.

Autonomous Driving Deblurring +2

KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning

1 code implementation CVPR 2022 Shyamgopal Karthik, Massimiliano Mancini, Zeynep Akata

The goal of open-world compositional zero-shot learning (OW-CZSL) is to recognize compositions of state and objects in images, given only a subset of them during training and no prior on the unseen compositions.

Compositional Zero-Shot Learning Missing Labels

Learning From Long-Tailed Data With Noisy Labels

no code implementations25 Aug 2021 Shyamgopal Karthik, Jérome Revaud, Boris Chidlovskii

In addition, the resulting learned representations are also remarkably robust to label noise, when fine-tuned with an imbalance- and noise-resistant loss function.

Self-Supervised Learning

No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks

1 code implementation1 Apr 2021 Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi

There has been increasing interest in building deep hierarchy-aware classifiers that aim to quantify and reduce the severity of mistakes, and not just reduce the number of errors.

Amending Mistakes Post-hoc in Deep Networks by Leveraging Class Hierarchies

no code implementations ICLR 2021 Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi

There has been increasing interest in building deep hierarchy-aware classifiers, aiming to quantify and reduce the severity of mistakes and not just count the number of errors.

Simple Unsupervised Multi-Object Tracking

no code implementations4 Jun 2020 Shyamgopal Karthik, Ameya Prabhu, Vineet Gandhi

Multi-object tracking has seen a lot of progress recently, albeit with substantial annotation costs for developing better and larger labeled datasets.

Multi-Object Tracking Object

Exploring 3 R's of Long-term Tracking: Re-detection, Recovery and Reliability

no code implementations27 Oct 2019 Shyamgopal Karthik, Abhinav Moudgil, Vineet Gandhi

Recent works have proposed several long term tracking benchmarks and highlight the importance of moving towards long-duration tracking to bridge the gap with application requirements.

Cannot find the paper you are looking for? You can Submit a new open access paper.